Abstract
Human genetic syndromes are often challenging to diagnose clinically. Facial phenotype is a key diagnostic indicator for hundreds of genetic syndromes and computer-assisted facial phenotyping is a promising approach to assist diagnosis. Most previous approaches to automated face-based syndrome diagnosis have analyzed different datasets of either 2D images or surface mesh-based 3D facial representations, making direct comparisons of performance challenging. In this work, we developed a set of subject-matched 2D and 3D facial representations, which we then analyzed with the aim of comparing the performance of 2D and 3D image-based approaches to computer-assisted syndrome diagnosis. This work represents the most comprehensive subject-matched analyses to date on this topic. In our analyses of 1907 subject faces representing 43 different genetic syndromes, 3D surface-based syndrome classification models significantly outperformed 2D image-based models trained and evaluated on the same subject faces. These results suggest that the clinical adoption of 3D facial scanning technology and continued collection of syndromic 3D facial scan data may substantially improve face-based syndrome diagnosis.
This is a preview of subscription content, access via your institution
Access options
Subscribe to this journal
Receive 12 print issues and online access
$259.00 per year
only $21.58 per issue
Buy this article
- Purchase on Springer Link
- Instant access to full article PDF
Prices may be subject to local taxes which are calculated during checkout
Similar content being viewed by others
Data availability
The 3D facial scan data used in this work is available through application to the Face Base consortium (www.facebase.org).
References
Thevenot J, Lopez M, Hadid A. A survey on computer vision for assistive medical diagnosis from faces. IEEE J Biomed Health Inform. 2018:22:1497–511.
Hennekam R, Allanson J, Krantz I. Gorlin’s Syndromes of the Head and Neck, Oxford University Press, 2010.
Hart T, Hart P. Genetic studies of craniofacial anomalies: clinical implications and applications. Orthod Craniofacial Res. 2009;12:212–20.
Matthews H, de Jong G, Maal T, Claes P. Static and motion facial analysis for craniofacial assessment and diagnosing diseases. Annu Rev Biomed Data Sci. 2022;5:19–42.
MacEachern SJ, Forkert ND. Machine learning for precision medicine. Genome. 2021;64:416–25.
Alsafar MCER, Werghi N, Al-Muhairi H, Alsafar H. Using facial images for the diagnosis of genetic syndromes: a survey. in International Conference on Communications, Signal Processing, and their Applications, 2015.
Gurovich Y, Hanani Y, Bar O, Nadav G, Fleischer N, Gelbman D, et al. Identifying facial phenotypes of genetic disorders using deep learning. Nat Med. 2019;25:60–4.
Hallgrímsson B, Aponte JD, Katz DC, Bannister JJ, Riccardi SL, Mahasuwan N, et al. Automated syndrome diagnosis by three-dimensional facial imaging. Genet Med. 2020;22:1–12.
Bannister J, Wilms M, Aponte D, Katz D, Klein OD, Bernier FP, et al. A deep invertible 3D facial shape model for interpretable genetic syndrome diagnosis. IEEE J Biomed Health Inform. 2022;26:3229–39.
Wilamowska K, Shapiro L, Heike C. Classification of 3D face shape in 22q11.2 deletion syndrome. in IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2009.
Anas I, Bamgbose B, Nuhu S. A comparison between 2D and 3D methods of quantifying facial morphology. Heliyon. 2019;5:e01880.
Zogheib T, Jacobs R, Bornstein M, Agbaje J, Anumendem D, Klazen Y, et al. Comparison of 3D scanning versus 2D photography for the identification of facial soft-tissue landmarks. Open Dent J. 2018;12:61–71.
Bilge AS, Sankur B, Taha M. Comparative evaluation of 3D vs. 2D modality for automatic detection of facial action units. Pattern Recognit. 2012;45:767–82.
Chang K, Bowyer K, Flynn P, Chen X. Multi-biometrics using facial appearance, shape and temperature. in Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004.
Zhou S, Xiao S. 3D face recognition: a survey. Hum-centric Comput Inform Sci. 2018;8. https://hcis-journal.springeropen.com/articles/10.1186/s13673-018-0157-2.
“Face ID Security,” 2017. [Online]. Available: www.apple.com/business-docs/FaceID_Security_Guide.pdf.
Hsieh T-C, Aviram B-H, Moosa S, Ehmke N, Gripp KW, Pantel JT, et al. GestaltMatcher facilitates rare disease matching using facial phenotype descriptors. Nat Genet. 2022;54:349–57.
Bannister JJ, Crites SR, Aponte JD, Katz DC, Wilms M, Klein OD, et al. Fully automatic landmarking of syndromic 3D facial surface scans using 2D images. Sensors. 2020;20:3171.
Amberg B, Romdhani S, Vetter T. Optimal Step Nonrigid ICP Algorithms for Surface Registration. in IEEE Conference on Computer Vision and Pattern Recognition, 2007.
Serengil SI, Ozpinar A. “LightFace: a hybrid deep face recognition framework,” in 2020 Innovations in Intelligent Systems and Applications Conference (ASYU), 2020.
Deng J, Guo J, Xue N, Zafeiriou S. ArcFace: Additive Angular Margin Loss for Deep Face Recognition. in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
Farkas LG, Katic MJ, Forrest CR. International anthropometric study of facial morphology in various ethnic groups/races. J Craniofacial Surg. 2005;16:615–46.
Berretti S, Del Bimbo A, Pala P. Distinguishing facial features for ethnicity-based 3D face recognition. ACM Trans Intell Syst Technol (TIST). 2012;3:1–20.
Funding
This research was funded by the National Institutes of Health (U01-DE024440), the Canada Research Chairs program, as well as by the River Fund at Calgary Foundation.
Author information
Authors and Affiliations
Contributions
(1) Research Project: A. Conception, B. Organization, C. Execution; (2) Statistical Analysis: A. Design, B. Execution, C. Review and Critique; (3) Manuscript: A. Writing of the First Draft, B. Review and Critique. JJB: 1A, 1B, 1C, 2A, 2B, 3A. DA: 1B, 1C, 2C, 3B. DK: 1B, 1C, 2C, 3B. ODK: 1A, 1B, 3B. FPJB: 1A, 1B, 3B. RAS: 1A, 1B, 3B. BH: 1A, 1B, 2A, 2C, 3B. NDF: 1A, 1B, 2A, 2C, 3B.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Ethics approval
This study was conducted in accordance with the Declaration of Helsinki. Ethics approval was granted by the Conjoint Health Research Ethics Board (CHREB# REB14-0340_REN4) at the University of Calgary. Informed consent informed was obtained from all subjects. Consent for the publication of facial images was obtained for the example subject shown in Figs. 1 and 3.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Bannister, J.J., Wilms, M., Aponte, J.D. et al. Comparing 2D and 3D representations for face-based genetic syndrome diagnosis. Eur J Hum Genet 31, 1010–1016 (2023). https://doi.org/10.1038/s41431-023-01308-w
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1038/s41431-023-01308-w
This article is cited by
-
Why donât we all use genomic testing?
European Journal of Human Genetics (2023)